End of training
Browse files- README.md +84 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: myBit-Llama2-jp-127M-test-3
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# myBit-Llama2-jp-127M-test-3
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 5.8378
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2.4e-05
|
| 38 |
+
- train_batch_size: 96
|
| 39 |
+
- eval_batch_size: 96
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: polynomial
|
| 43 |
+
- lr_scheduler_warmup_steps: 250
|
| 44 |
+
- num_epochs: 1
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 10.1753 | 0.04 | 100 | 9.3900 |
|
| 51 |
+
| 9.0259 | 0.07 | 200 | 8.5694 |
|
| 52 |
+
| 8.0861 | 0.11 | 300 | 7.5814 |
|
| 53 |
+
| 7.2827 | 0.15 | 400 | 7.0210 |
|
| 54 |
+
| 6.9154 | 0.18 | 500 | 6.7973 |
|
| 55 |
+
| 6.738 | 0.22 | 600 | 6.6274 |
|
| 56 |
+
| 6.6074 | 0.26 | 700 | 6.5311 |
|
| 57 |
+
| 6.5101 | 0.29 | 800 | 6.4338 |
|
| 58 |
+
| 6.4433 | 0.33 | 900 | 6.3696 |
|
| 59 |
+
| 6.382 | 0.36 | 1000 | 6.3051 |
|
| 60 |
+
| 6.3157 | 0.4 | 1100 | 6.2578 |
|
| 61 |
+
| 6.2805 | 0.44 | 1200 | 6.2139 |
|
| 62 |
+
| 6.2317 | 0.47 | 1300 | 6.1715 |
|
| 63 |
+
| 6.2085 | 0.51 | 1400 | 6.1438 |
|
| 64 |
+
| 6.1702 | 0.55 | 1500 | 6.1099 |
|
| 65 |
+
| 6.1337 | 0.58 | 1600 | 6.0789 |
|
| 66 |
+
| 6.113 | 0.62 | 1700 | 6.0530 |
|
| 67 |
+
| 6.0663 | 0.66 | 1800 | 6.0150 |
|
| 68 |
+
| 6.0446 | 0.69 | 1900 | 5.9880 |
|
| 69 |
+
| 6.0267 | 0.73 | 2000 | 5.9568 |
|
| 70 |
+
| 5.9972 | 0.77 | 2100 | 5.9274 |
|
| 71 |
+
| 5.9599 | 0.8 | 2200 | 5.9109 |
|
| 72 |
+
| 5.9369 | 0.84 | 2300 | 5.8884 |
|
| 73 |
+
| 5.9266 | 0.88 | 2400 | 5.8689 |
|
| 74 |
+
| 5.9068 | 0.91 | 2500 | 5.8548 |
|
| 75 |
+
| 5.9091 | 0.95 | 2600 | 5.8462 |
|
| 76 |
+
| 5.879 | 0.99 | 2700 | 5.8378 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.38.2
|
| 82 |
+
- Pytorch 2.1.0+cu121
|
| 83 |
+
- Datasets 2.18.0
|
| 84 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.38.2"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 511344824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9cd2014d3db3cb8348951bbe3c771fb4b9c89741cbffbf2bddc773e9245154c
|
| 3 |
size 511344824
|